{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:YZ4S23WOBBJ4U4WJ7XXK37XC3P","short_pith_number":"pith:YZ4S23WO","canonical_record":{"source":{"id":"1301.0601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:58:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c1b8da872c9071bc0dc6abb6d4db3b735ed0b4a661f856157aa3fc5af4bfe08","abstract_canon_sha256":"87c89fec97599fa210332ea12a00acff8806bb1c7a416f415ec8ae82bf1a5ae2"},"schema_version":"1.0"},"canonical_sha256":"c6792d6ece0853ca72c9fdeeadfee2dbe4676ca6386f7cd8f2d0f221988c8d47","source":{"kind":"arxiv","id":"1301.0601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0601","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0601v1","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0601","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"YZ4S23WOBBJ4","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"YZ4S23WOBBJ4U4WJ","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"YZ4S23WO","created_at":"2026-05-18T12:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:YZ4S23WOBBJ4U4WJ7XXK37XC3P","target":"record","payload":{"canonical_record":{"source":{"id":"1301.0601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:58:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c1b8da872c9071bc0dc6abb6d4db3b735ed0b4a661f856157aa3fc5af4bfe08","abstract_canon_sha256":"87c89fec97599fa210332ea12a00acff8806bb1c7a416f415ec8ae82bf1a5ae2"},"schema_version":"1.0"},"canonical_sha256":"c6792d6ece0853ca72c9fdeeadfee2dbe4676ca6386f7cd8f2d0f221988c8d47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:18.222340Z","signature_b64":"8qoco3DCg09vT5nw57fr0ikhyMS7gXspShqC+Con72ALJNj17PYcKA2RUz58c4QYou5U3Xa9iuas7YQtAcFICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6792d6ece0853ca72c9fdeeadfee2dbe4676ca6386f7cd8f2d0f221988c8d47","last_reissued_at":"2026-05-18T03:37:18.221834Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:18.221834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.0601","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7UUOhRKSPeS36AiN7IOFgXqjY6lmzBGcbXGqqb1lbqZ5yql624LhjqGjmm1wteGZ4PH/oKgQbtiLhlrbKuNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:02:33.463756Z"},"content_sha256":"3f956d116bffb81eb85a97f460864f36fd3bcf55e3987e7c3ac7fc6c78a38ccf","schema_version":"1.0","event_id":"sha256:3f956d116bffb81eb85a97f460864f36fd3bcf55e3987e7c3ac7fc6c78a38ccf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:YZ4S23WOBBJ4U4WJ7XXK37XC3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Partially Known World Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian R. Shelton","submitted_at":"2012-12-12T15:58:25Z","abstract_excerpt":"Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics.  Partially observable Markov decision processes (POMDPs) allow for the modeling of both.  Unfortunately, they do not provide a natural framework in which to specify knowledge about the domain dynamics.  The designer must either admit to knowing nothing about the dynamics or completely specify the dynamics (thereby turning it into a planning problem).  We propose a new framework called a partia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0601","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fad/VXN2t9l8Y7O59YzQt9T39kc+rBGRGJJPZnYRX9aUsa6G2Z+k6wUO2eKusxljpnD49eX7Xm1svhrPKShVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:02:33.464453Z"},"content_sha256":"6abafe21ae02e52b0f734494669f1e65ab212595776d06cc0a40cf150db02b76","schema_version":"1.0","event_id":"sha256:6abafe21ae02e52b0f734494669f1e65ab212595776d06cc0a40cf150db02b76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/bundle.json","state_url":"https://pith.science/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T09:02:33Z","links":{"resolver":"https://pith.science/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P","bundle":"https://pith.science/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/bundle.json","state":"https://pith.science/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZ4S23WOBBJ4U4WJ7XXK37XC3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:YZ4S23WOBBJ4U4WJ7XXK37XC3P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"87c89fec97599fa210332ea12a00acff8806bb1c7a416f415ec8ae82bf1a5ae2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:58:25Z","title_canon_sha256":"2c1b8da872c9071bc0dc6abb6d4db3b735ed0b4a661f856157aa3fc5af4bfe08"},"schema_version":"1.0","source":{"id":"1301.0601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0601","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0601v1","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0601","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"YZ4S23WOBBJ4","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"YZ4S23WOBBJ4U4WJ","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"YZ4S23WO","created_at":"2026-05-18T12:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:6abafe21ae02e52b0f734494669f1e65ab212595776d06cc0a40cf150db02b76","target":"graph","created_at":"2026-05-18T03:37:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics.  Partially observable Markov decision processes (POMDPs) allow for the modeling of both.  Unfortunately, they do not provide a natural framework in which to specify knowledge about the domain dynamics.  The designer must either admit to knowing nothing about the dynamics or completely specify the dynamics (thereby turning it into a planning problem).  We propose a new framework called a partia","authors_text":"Christian R. Shelton","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:58:25Z","title":"Reinforcement Learning with Partially Known World Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0601","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3f956d116bffb81eb85a97f460864f36fd3bcf55e3987e7c3ac7fc6c78a38ccf","target":"record","created_at":"2026-05-18T03:37:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"87c89fec97599fa210332ea12a00acff8806bb1c7a416f415ec8ae82bf1a5ae2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:58:25Z","title_canon_sha256":"2c1b8da872c9071bc0dc6abb6d4db3b735ed0b4a661f856157aa3fc5af4bfe08"},"schema_version":"1.0","source":{"id":"1301.0601","kind":"arxiv","version":1}},"canonical_sha256":"c6792d6ece0853ca72c9fdeeadfee2dbe4676ca6386f7cd8f2d0f221988c8d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6792d6ece0853ca72c9fdeeadfee2dbe4676ca6386f7cd8f2d0f221988c8d47","first_computed_at":"2026-05-18T03:37:18.221834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:37:18.221834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qoco3DCg09vT5nw57fr0ikhyMS7gXspShqC+Con72ALJNj17PYcKA2RUz58c4QYou5U3Xa9iuas7YQtAcFICQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:37:18.222340Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.0601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f956d116bffb81eb85a97f460864f36fd3bcf55e3987e7c3ac7fc6c78a38ccf","sha256:6abafe21ae02e52b0f734494669f1e65ab212595776d06cc0a40cf150db02b76"],"state_sha256":"d3635462c3416099f9b9eeb7914948ef1183a26752fff15ff315b4dc75ade978"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"524D/xF94yIqdWgQTZsVHr9Hm01SggryY1ErrsrNtCAuG0835ijTLOVlFbJde/CShCwrjuH0WlUoqGxzaqpYCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:02:33.467515Z","bundle_sha256":"66cf3db958713ecae445e6544d45bb53125202326c32a4b9aeeaa7a89eef65f1"}}